Cooper Leong's picture

1 9 29

Cooper Leong

cooperleong00

·

https://cooperleong00.github.io/

AI & ML interests

None yet

Recent Activity

liked a dataset about 3 hours ago

edinburgh-dawg/mmlu-redux-2.0

upvoted a paper 4 days ago

Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region

commented on a paper 4 days ago

Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region

View all activity

Organizations

None yet

Collections 1

Papers 4

arxiv:2411.07618

arxiv:2410.06638

arxiv:2409.03256

arxiv:2310.09573

models 3

cooperleong00/Qwen2.5-7B-Instruct-Jailbroken

Updated Dec 23, 2024 • 34 • 1

cooperleong00/Meta-Llama-3-8B-Instruct-Jailbroken

Updated Dec 23, 2024 • 35 • 2

cooperleong00/deberta-v3-large_toxicity-scorer

Text Classification • Updated Feb 29, 2024 • 675 • 4

datasets

None public yet